Artificial Intelligence in Refractive surgery: Prediction, Simulation, and Explainability

 Existing system indicates that the development of AI in refractive surgery goes beyond improved predictive accuracy and marks a shift towards more personalized approaches to eye care. These reviewed studies show that AI is increasingly helping  the ophthalmologists by analysing complex corneal and biometric patterns. The existing system support decision – making, point out subtle risk factors, and provide personalized surgical insight; this will help the surgeons to have a more informed plan. Artificial intelligence also supports treatment decisions with respect to individual corneal structure, healing response and visual need rather than general guidelines. Additionally, generative modelling and explainability are changing how outcomes are communicated, allowing patients to see what a procedure might achieve and understanding the reason behind specific recommendations. Although there are still challenges, the direction of current research shows that AI will serve as a reliable tool.

B. Gurnani and K. Kaur, “Recent Advances in Refractive Surgery: An Overview.,” Clinical Ophthalmology, vol. 18, 2024. Fan-Paul and Nancy I. et al, “Night Vision Disturbances After Corneal Refractive Surgery,” Survey of Ophthalmology, vol. 47, no. 6, pp. 533-546, 2002. D. Sk., “Post-refractive Surgery Dry Eye: A Systematic Review Exploring Pathophysiology, Risk Factors, and Novel Management Strategies.,” Cureus, 2024. M. T. A. B. N. L. H. M. S. R. Y. &. H. P. Moshirfar, “Ectasia After Corneal Refractive Surgery: A Systematic Review,” Ophthalmology and Therapy, vol. 10, pp. 753 - 776, 2021. Q. Y. S. T. J. W. R. T. J. M. K. Y. H. &. D. Y. P. Wan, “Prediction of Early Visual Outcome of Small-Incision Lenticule Extraction (SMILE) Based on Deep Learning.,” Ophthalmology and therapy, vol. 12(2), p. 1263–1279, 2023. Z. L. Y. X. W. X. Y. Y. H. X. L. F. X. J. L. L. L. H. F. Q. L. H. L. Q. Xie Y, “Screening Candidates for Refractive Surgery With Corneal Tomographic-Based Deep Learning.,” JAMA Ophthalmol., vol. 138, no. 5, pp. 519-526, 2020. I. H. R. H. C. J. K. K. I. S. L. J. S. K. G. L. T. H. R. Tae Keun Yoo, “Explainable Machine Learning Approach as a Tool to Understand Factors Used to Select the Refractive Surgery Technique on the Expert Level,” Trans. Vis. Sci. Tech., vol. 9, no. 2, 2020. Z. Z. J. P. X.-N. L. W.-Y. C. G.-H. Z. W.-H. Y. Nan Cheng, “"MCSTransWnet: A new deep learning process for postoperative corneal topography prediction based on raw multimodal data from the Pentacam HR system",” Medicine in Novel Technology and Devices, vol. 21, 2024. S. Y. Y. S. Z. L. L. W. P. Z. J. &. Y. Y. Zhang, “Development of risk prediction model for small incision lenticule extraction,” Frontiers in medicine, vol. 12, 2025. J. e. a. Kim, “Machine learning predicting myopic regression after corneal refractive surgery using preoperative data and fundus photography.,” Graefe's archive for clinical and experimental ophthalmology, vol. 260, no. 11, 2022.